Role overview
- Design and implement agent workflows focusing on context engineering, tool use, and orchestration.
- Build retrieval and memory systems, integrating vector search, session + long-term memory, and compaction algorithms.
- Develop evaluation pipelines, creating both automated and human-led evaluation suites to maintain high performance and safety.
- Integrate AI services on cloud platforms, utilizing AWS Bedrock, Knowledge Bases, and associated Agent frameworks.
- Collaborate closely with business stakeholders to understand functional needs and build aligned, production-grade tools.
Responsibilities
- Architecting and deploying reliable, secure, and scalable LLM-driven applications.
- Ensuring the structural integrity and speed of retrieval-augmented generation (RAG) pipelines.
- Setting up rigorous quality metrics and observability frameworks to monitor AI system behaviors.
- Translating complex user requirements into clean, modular, and maintainable Python codebases.
- Hands-on experience interfacing with Large Language Models (LLMs) via APIs, SDKs, and open-source packages.
- Proven experience building agent-based systems, specifically handling memory persistence, tool orchestration, and multi-step workflows.
- Strong knowledge of retrieval systems, embedding models, vector databases, and semantic search optimization.
- Familiarity with evaluation frameworks and quality measurement paradigms tailored for generative AI systems.
- Cloud expertise working with AWS Bedrock; experience with AWS AgentCore is highly preferred (a strong pre).
- Strong software engineering background, with expert proficiency in Python, object-oriented/functional programming patterns, and robust version control (Git).
- An analytical problem-solver who enjoys working at the frontier of technology and business strategy.
- Excellent communication skills with the ability to explain complex AI engineering concepts to non-technical stakeholders.
- A collaborative team player who thrives in a fast-paced environment and is passionate about building clean, production-grade software.
- Eager to stay ahead of the curve in a rapidly evolving generative AI landscape.
About the company
Since 2000 we provide professional solutions to organizations ranging from tech start-ups to global players. From our offices in Amsterdam and London we have built an international and local network of skilled employed professionals and contractors fuelled by our passion for connecting skills with projects. Over the years we have fulfilled over 1700 requirements and nowadays we consistently have 250+ professionals recruited and relocated from 14 countries allocated to various projects. Our strength is the way that we see and treat people. This will always be a key factor in our strategy for many years to come.
Tags & focus areas
Used for matching and alerts on DevFound Ai Ai Engineer